Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.20852 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911896697831424 |
|---|---|
| author | Cheng, Xuxin Xu, Wanshi Zhu, Zhihong Li, Hongxiang Zou, Yuexian |
| author_facet | Cheng, Xuxin Xu, Wanshi Zhu, Zhihong Li, Hongxiang Zou, Yuexian |
| contents | Spoken language understanding (SLU) is a core task in task-oriented dialogue systems, which aims at understanding the user's current goal through constructing semantic frames. SLU usually consists of two subtasks, including intent detection and slot filling. Although there are some SLU frameworks joint modeling the two subtasks and achieving high performance, most of them still overlook the inherent relationships between intents and slots and fail to achieve mutual guidance between the two subtasks. To solve the problem, we propose a multi-level multi-grained SLU framework MMCL to apply contrastive learning at three levels, including utterance level, slot level, and word level to enable intent and slot to mutually guide each other. For the utterance level, our framework implements coarse granularity contrastive learning and fine granularity contrastive learning simultaneously. Besides, we also apply the self-distillation method to improve the robustness of the model. Experimental results and further analysis demonstrate that our proposed model achieves new state-of-the-art results on two public multi-intent SLU datasets, obtaining a 2.6 overall accuracy improvement on the MixATIS dataset compared to previous best models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20852 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning Cheng, Xuxin Xu, Wanshi Zhu, Zhihong Li, Hongxiang Zou, Yuexian Computation and Language Spoken language understanding (SLU) is a core task in task-oriented dialogue systems, which aims at understanding the user's current goal through constructing semantic frames. SLU usually consists of two subtasks, including intent detection and slot filling. Although there are some SLU frameworks joint modeling the two subtasks and achieving high performance, most of them still overlook the inherent relationships between intents and slots and fail to achieve mutual guidance between the two subtasks. To solve the problem, we propose a multi-level multi-grained SLU framework MMCL to apply contrastive learning at three levels, including utterance level, slot level, and word level to enable intent and slot to mutually guide each other. For the utterance level, our framework implements coarse granularity contrastive learning and fine granularity contrastive learning simultaneously. Besides, we also apply the self-distillation method to improve the robustness of the model. Experimental results and further analysis demonstrate that our proposed model achieves new state-of-the-art results on two public multi-intent SLU datasets, obtaining a 2.6 overall accuracy improvement on the MixATIS dataset compared to previous best models. |
| title | Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.20852 |